<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="prama-2025-llms">
    <titleInfo>
        <title>LLMs for Low-Resource Dialect Translation Using Context-Aware Prompting: A Case Study on Sylheti</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tabia</namePart>
        <namePart type="given">Tanzin</namePart>
        <namePart type="family">Prama</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Firoj</namePart>
            <namePart type="family">Alam</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sudipta</namePart>
            <namePart type="family">Kar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shammur</namePart>
            <namePart type="given">Absar</namePart>
            <namePart type="family">Chowdhury</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naeemul</namePart>
            <namePart type="family">Hassan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Enamul</namePart>
            <namePart type="given">Hoque</namePart>
            <namePart type="family">Prince</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohiuddin</namePart>
            <namePart type="family">Tasnim</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Md</namePart>
            <namePart type="given">Rashad</namePart>
            <namePart type="given">Al</namePart>
            <namePart type="given">Hasan</namePart>
            <namePart type="family">Rony</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Md</namePart>
            <namePart type="given">Tahmid</namePart>
            <namePart type="given">Rahman</namePart>
            <namePart type="family">Rahman</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Mumbai, India</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-314-2</identifier>
    </relatedItem>
    <abstract>Large Language Models (LLMs) have demonstrated strong translation abilities through prompting, even without task-specific training. However, their effectiveness in dialectal and low-resource contexts remains underexplored. This study presents the first systematic investigation of LLM-based Machine Translation (MT) for Sylheti, a dialect of Bangla that is itself low-resource. We evaluate five advanced LLMs (GPT-4.1, GPT-4.1-mini, LLaMA 4, Grok 3, and Deepseek V3.2) across both translation directions (Bangla \ensuremathłeftrightarrow Sylheti), and find that these models struggle with dialect-specific vocabulary. To address this, we introduce Sylheti-CAP (Context-Aware Prompting), a three-step framework that embeds a linguistic rulebook, dictionary (core vocabulary and idioms), and authenticity check directly into prompts. Extensive experiments show that Sylheti-CAP consistently improves translation quality across models and prompting strategies. Both automatic metrics and human evaluations confirm its effectiveness, while qualitative analysis reveals notable reductions in hallucinations, ambiguities, and awkward phrasing—establishing Sylheti-CAP as a scalable solution for dialectal and low-resource MT.</abstract>
    <identifier type="citekey">prama-2025-llms</identifier>
    <location>
        <url>https://aclanthology.org/2025.banglalp-1.24/</url>
    </location>
    <part>
        <date>2025-12</date>
        <extent unit="page">
            <start>292</start>
            <end>308</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T LLMs for Low-Resource Dialect Translation Using Context-Aware Prompting: A Case Study on Sylheti
%A Prama, Tabia Tanzin
%Y Alam, Firoj
%Y Kar, Sudipta
%Y Chowdhury, Shammur Absar
%Y Hassan, Naeemul
%Y Prince, Enamul Hoque
%Y Tasnim, Mohiuddin
%Y Rony, Md Rashad Al Hasan
%Y Rahman, Md Tahmid Rahman
%S Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-314-2
%F prama-2025-llms
%X Large Language Models (LLMs) have demonstrated strong translation abilities through prompting, even without task-specific training. However, their effectiveness in dialectal and low-resource contexts remains underexplored. This study presents the first systematic investigation of LLM-based Machine Translation (MT) for Sylheti, a dialect of Bangla that is itself low-resource. We evaluate five advanced LLMs (GPT-4.1, GPT-4.1-mini, LLaMA 4, Grok 3, and Deepseek V3.2) across both translation directions (Bangla \ensuremathłeftrightarrow Sylheti), and find that these models struggle with dialect-specific vocabulary. To address this, we introduce Sylheti-CAP (Context-Aware Prompting), a three-step framework that embeds a linguistic rulebook, dictionary (core vocabulary and idioms), and authenticity check directly into prompts. Extensive experiments show that Sylheti-CAP consistently improves translation quality across models and prompting strategies. Both automatic metrics and human evaluations confirm its effectiveness, while qualitative analysis reveals notable reductions in hallucinations, ambiguities, and awkward phrasing—establishing Sylheti-CAP as a scalable solution for dialectal and low-resource MT.
%U https://aclanthology.org/2025.banglalp-1.24/
%P 292-308

Markdown (Informal)

[LLMs for Low-Resource Dialect Translation Using Context-Aware Prompting: A Case Study on Sylheti](https://aclanthology.org/2025.banglalp-1.24/) (Prama, BanglaLP 2025)

• LLMs for Low-Resource Dialect Translation Using Context-Aware Prompting: A Case Study on Sylheti (Prama, BanglaLP 2025)

ACL

• Tabia Tanzin Prama. 2025. LLMs for Low-Resource Dialect Translation Using Context-Aware Prompting: A Case Study on Sylheti. In Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025), pages 292–308, Mumbai, India. Association for Computational Linguistics.